摘要
以来水来沙、水流主流位置变化及河道边界条件为输入向量,在对水沙作用强度和护岸工程对河道崩岸的作用进行定量化处理的同时,以河道崩岸为输出向量,研究建立了基于BP神经网络的河道崩岸预测模型.利用此模型对荆江石首弯道1965～2003年的崩岸情况进行了模拟和预测.计算结果表明,该模型能较准确地模拟和预测河道崩岸变化.该模型的建立为河道崩岸的预测预报提供了一个新途径.
By using flow and sediment conditions and position of main flow and river boundary as the input vectors, through analyzing influences of flow and sediment intensity and bank-protection works on bank-failure, bank-failure is used as output, so a prediction model for river bank-failure is established based on BP neural networks. The model is used to simulate the bank-failure of Shishou reach bends at Jingjiang River from 1965 to 2003; the results show that the model can simulate and predict the bank-failure with good precision. The model also provides a new method to predict river bank-failure.
出处
《武汉大学学报（工学版）》
CAS
CSCD
北大核心
2004年第6期9-12,21,共5页
Engineering Journal of Wuhan University
基金
教育部重点科技项目(02134)
国家自然科学基金项目(50279035).
关键词
河道崩岸
水沙作用强度
BP神经网络
预测模型
river bank-failure
flow and sediment intensity
BP neural networks
prediction model
